artsonia-mcp: Instructions file for Claude Code

CLAUDE.md

artsonia-mcp CLAUDE.md is an instructions file for Claude Code from chrischall/artsonia-mcp. It costs 5,565 tokens per session, scanned A, original, MIT.

A repository-specific instruction guide for Claude Code, an AI coding assistant. It explains an Artsonia MCP server, which connects the assistant to children’s artwork portfolios on Artsonia, including its login, scraping, tools, and two transport modes.

In plain words
What is it for?
Use it when working on this Artsonia server, especially its client, authentication, transport modes, portfolio features, or confirm-gated write operations.
Why use it?
It gives the coding assistant the project’s architecture and authentication rules so changes fit the existing design and handle its private website session correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is chrischall/artsonia-mcp's own configuration. It tells Claude Code how to work on artsonia-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything artsonia-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chrischall/artsonia-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/chrischall/artsonia-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/chrischall/artsonia-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for artsonia-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chrischall/artsonia-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/chrischall/artsonia-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chrischall/artsonia-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/artsonia-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for artsonia-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chrischall/artsonia-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/artsonia-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,565 This file is loaded in full into every session.
When invoked 5,565 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.05565 $0.05565
Opus 5.5 $0.02226 $0.02226
Sonnet 5.5 $0.01113 $0.01113
Haiku 4.5 $0.00556 $0.00556

Measured today against content hash 95e8dfd90f58, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

artsonia-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

TL;DR

MCP server for Artsonia (artsonia.com — kids' artwork portfolios). Cookie-session archetype: there is no public API, so the server logs into the parent/fan website with a username + password, harvests the resulting HttpOnly session cookie, and scrapes/POSTs the member pages. 15 tools across students, portfolio/artwork, comments, fans, teacher feedback, awards, account profile, image downloads, and a small set of writes (two of them confirmation-gated).

Two transport modes, selected by ARTSONIA_TRANSPORT:

  1. fetch (default, direct) — Node fetch against the site. The server owns the session: AuthManager runs the username/password login (POST /members/login.asp), keeps the cookie jar, and re-logs-in once on expiry.
  2. fetchproxy (optional, browser-session) — requests ride the user's already-signed-in browser tab via @fetchproxy/server. The browser carries the session, so the server-side login is skipped entirely (usesBrowserSession = true). No ARTSONIA_USERNAME/PASSWORD needed in this mode.

Auth resolution

src/auth.ts owns the username/password login and the cookie session. It delegates the single-flight login + invalidate/re-login + one-replay-on-expiry to the shared CookieSessionManager from @chrischall/mcp-utils/session, typed over ArtsoniaResponse so the custom transport's response flows through withSession() untouched.

  • Env vars: ARTSONIA_USERNAME + ARTSONIA_PASSWORD (required in direct mode), ARTSONIA_TRANSPORT (fetch default | fetchproxy), ARTSONIA_WS_PORT (fetchproxy WebSocket port override; default 37149 — a shared fleet port, do NOT change), ARTSONIA_INLINE_DOWNLOADS (1/true/yes/on ⇒ inline image downloads; unset/false ⇒ disk, except on a hosted deployment, which is always inline — see "Download I/O" below), ARTSONIA_OUTPUT_DIR (folders the disk IO may write dest into; default ~/Downloads + ~/Pictures — downloadRoots() in make-download-io.ts; its $MCP_DATA_DIR/downloads branch is no longer reached, since a hosted deployment never gets the disk IO), ARTSONIA_SESSION_CACHE (false disables the on-disk session cache; default on, direct mode only) and ARTSONIA_SESSION_FILE (override the cache path; defaults to $MCP_DATA_DIR/.artsonia-mcp/session-<user>.json, one file PER USER so createDirectClient callers do not clobber each other).
  • Deferred config error: the client is a module singleton constructed in src/client.ts (NOT index.ts), so the server boots and answers the host's install-time tools/list probe even with no creds. The missing-creds error is cached as a permanent error (CONFIG_ERROR_MARKER) and only surfaces on the first tool call — every later ensure() rethrows it rather than retrying a login that can never succeed.
  • Login success marker: doLogin() POSTs Username/Password/TargetUrl=/members//Action=login with redirect: 'manual' and treats a 301/302 whose Location is NOT login.asp (plus a non-empty cookie jar) as success. Magic-link-only accounts are unsupported.
  • Expiry heuristic (looksUnauthenticated): Artsonia expires by redirecting/rendering back to the login page (NOT a 401). Detected from the final URL, a manual 3xx Location pointing at login.asp, or the login form structure rendered in place (<form action="…login.asp"> plus a name="Password" field), via the shared structural looksLikeLoginPage from @chrischall/mcp-utils/session (no status code counts by itself). Never from body prose — artwork pages carry user-generated text (fan comments, titles), and a comment saying "You need to log in" must not force a re-login or a false bad-credentials error.

Read the full file on GitHub · 164 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today Changed · +130 tokens per session 95e8dfd90f58
  2. 3d ago Changed · +2 lines · +112 tokens per session 01d171c549cd
  3. 29d ago Changed · -63 tokens per session eef2bdb20aaf
  4. 1mo ago Changed · +12 tokens per session c460f23d39b7
  5. 1mo ago Changed · +202 tokens per session ae2a5c062d95
  6. 1mo ago Changed · +45 tokens per session 64d661802584
  7. 1mo ago Changed · +280 tokens per session 4e981ff0cf50
  8. 2mo ago First seen · 162 lines · 4,847 tokens per session scan A f21745216162

Subscribe to this mod's changes

artsonia-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/artsonia-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 5,565 tokens to every session, about $0.0223 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

artsonia-mcp CLAUDE.md compared with instructions from other repositories

artsonia-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
artsonia-mcp CLAUDE.mdchrischall/artsonia-mcpInstructions file1yesterdayMITA5,565Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot